# Some Dialects Are More Equal Than Others: Non-Prestigious Arabic Dialectal Bias in LLMs

arXiv: https://arxiv.org/abs/2609.23955 · HTML: https://mlsanity.com/paper/2609.23955/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 31 references that are in the map.
- First posted on arXiv 21 Sep 2026.

## Builds on (most cited first, 11 of 11)

- [Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies](https://mlsanity.com/paper/1611.01368/) (2016)
- [ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic](https://mlsanity.com/paper/2402.12840/) (2024)
- [Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination](https://mlsanity.com/paper/2406.08818/) (2024)
- [AraDiCE: Benchmarks for Dialectal and Cultural Capabilities in LLMs](https://mlsanity.com/paper/2409.11404/) (2024)
- [Assessing Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks](https://mlsanity.com/paper/2410.11005/) (2024)
- [Social Bias in Large Language Models For Bangla: An Empirical Study on Gender and Religious Bias](https://mlsanity.com/paper/2407.03536/) (2024)
- [Large Language Models Discriminate Against Speakers of German Dialects](https://mlsanity.com/paper/2509.13835/) (2025)
- [JASMINE: Arabic GPT Models for Few-Shot Learning](https://mlsanity.com/paper/2212.10755/) (2022)
- [Nile-Chat: Egyptian Language Models for Arabic and Latin Scripts](https://mlsanity.com/paper/2507.04569/) (2025)
- [DialectalArabicMMLU: Benchmarking Dialectal Capabilities in Arabic and Multilingual Language Models](https://mlsanity.com/paper/2510.27543/) (2025)
- [Analyzing Dialectical Biases in LLMs for Knowledge and Reasoning Benchmarks](https://mlsanity.com/paper/2510.00962/) (2025)

## Abstract (arXiv)

Previous work on Egyptian Arabic in NLP has focused largely on the prestigious Cairene Egyptian Arabic (CEA) dialect, resulting in a lack of representation for the less prestigious Sa'idi Egyptian Arabic (SEA) dialect both in LLM and resource development. Does this lack of representation influence an LLM's view of the acceptability of SEA (upstream), and does an upstream bias against SEA lead to worse performance (downstream)? We investigate the upstream effect of SEA dialectal features on LLM preferences in a Targeted Syntactic Evaluation (TSE) task which reveals a significant bias against SEA across multiple LLMs. We then analyze the effect of these same features on downstream model performance on MMLU benchmarks and show that models experience a degradation in performance when presented with SEA. This work highlights the need for further exploration on how sub-dialectal variation impacts language technologies.